{"id":141196,"date":"2024-04-24T10:40:54","date_gmt":"2024-04-24T14:40:54","guid":{"rendered":"https:\/\/www.ucf.edu\/news\/?p=141196"},"modified":"2025-06-17T13:54:50","modified_gmt":"2025-06-17T17:54:50","slug":"computer-vision-researcher-develops-privacy-software-for-surveillance-videos","status":"publish","type":"post","link":"https:\/\/www.ucf.edu\/news\/computer-vision-researcher-develops-privacy-software-for-surveillance-videos\/","title":{"rendered":"Computer Vision Researcher Develops Privacy Software for Surveillance Videos"},"content":{"rendered":"
Computer vision can be a valuable tool for anyone tasked with analyzing hours of footage because it can speed up the process of identifying individuals. For example, law enforcement may use it to perform a search for individuals with a simple query, such as \u201cLocate anyone wearing a red scarf over the past 48 hours.\u201d<\/p>\n
With video surveillance becoming more and more ubiquitous, UCF Center for Research in Computer Vision (CRCV) Assistant Professor Yogesh Rawat, and his collaborators Mubarak Shah and Chen Chen, are working to address privacy issues with advanced software installed on video cameras. Their work is supported by $200,000 in funding from the U.S. National Science Foundation\u2019s Accelerating Research Translation (NSF ART) program.<\/p>\n
\u201cAutomation allows us to watch a lot of footage, which is not possible by humans,\u201d Rawat says. \u201cSurveillance is important for society, but there are always privacy concerns. This development will enable surveillance with privacy preservation.\u201d<\/p>\n
His video monitoring software protects the privacy of those recorded by obscuring select elements, such as faces or clothing, both in recordings and in real time. Rawat explains that his software adds perturbations to the RGB pixels in the video feed \u2013 the red, green and blue colors of light \u2013 so that human eyes are unable to recognize them.<\/p>\n
\u201cMainly we are interested in any identifiable information that we can visually interpret,\u201d Rawat says. \u201cFor example, for a person\u2019s face, I can say \u2018This is that individual,\u2019 just by identifying the face. It could be the height as well, maybe hair color, hair style, body shape — all those things that can be used to identify any person. All of this is private information.\u201d<\/p>\n